Exploratory Analysis

Clean data:

• Clean names
• Select relevant predictors & outcomes
• Drop neighborhoods that have no population

plots_df = read_excel("./data/nta-metadata.xlsx", sheet = "NTA Data") %>%
  janitor::clean_names() %>%
  select(nta_name, nta_code, total_pop, hispanic:other_race, poverty, smm, gonorrhea, health_ins, edu_less_than_hs, preterm_births, late_no_prenatal_care, medicaid_enroll) %>%
  drop_na(total_pop) %>% 
    mutate(poverty_level = cut(poverty, breaks = c(-Inf, 10, 20, 30, 40, Inf), labels = c("poverty_10","poverty_20", "poverty_30", "poverty_40", "poverty_40+"))) %>% 
  pivot_longer(
   cols = hispanic:other_race,
   names_to = "race",
   values_to = "percent_pop",
   values_drop_na = TRUE
 ) 

Outcome: SMM

poverty Vs SMM

poverty_smm_ggplot = 
  plots_df %>% 
  ggplot(aes(x = poverty, y = smm), group = nta_name) +
  geom_point(color = "red")

ggplotly(poverty_smm_ggplot)

poverty2_smm_ggplot = 
  plots_df %>% 
  ggplot(aes(x = poverty_level, y = smm)) + 
  geom_boxplot()

ggplotly(poverty2_smm_ggplot)

## Warning: Removed 25 rows containing non-finite values (stat_boxplot).

late or no prenatal care vs SMM

prenatal_care_ggplot = 
  plots_df %>% 
  ggplot(aes(x = late_no_prenatal_care, y = smm, group = nta_name)) + 
  geom_point(color = "red")

ggplotly(prenatal_care_ggplot)

## Warning: `group_by_()` is deprecated as of dplyr 0.7.0.
## Please use `group_by()` instead.
## See vignette('programming') for more help
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

Outcome: Gonorrhea

gonorrhea vs health insurance

gonorrhea1_ggplot = 
  plots_df %>% 
  ggplot(aes(x = health_ins, y = gonorrhea), group = nta_name) + 
  geom_point(color = "green")

ggplotly(gonorrhea1_ggplot)

gonorrhea vs medicaid

gonorrhea2_ggplot = 
  plots_df %>% 
  ggplot(aes(x = medicaid_enroll, y = gonorrhea), group = nta_name) +
  geom_point(color = "green")

ggplotly(gonorrhea2_ggplot)

gonorrhea vs education level

gonorrhea3_ggplot = 
  plots_df %>% 
  ggplot(aes(x = edu_less_than_hs, y = gonorrhea), group = nta_name) +
  geom_point(color = "green") 


ggplotly(gonorrhea3_ggplot)

Outcome: Preterm Births

health insurance vs preterm birth

preterm_ggplot = 
  plots_df %>% 
  ggplot(aes(x = health_ins, y = preterm_births), group = nta_name) +
  geom_point(color = "blue")

ggplotly(preterm_ggplot)

medicaid enrollment vs preterm birth

preterm2_ggplot = 
  plots_df %>% 
  ggplot(aes(x = medicaid_enroll, y = preterm_births, group = nta_name)) + 
  geom_point(color = "blue")

ggplotly(preterm2_ggplot)

late or no prenatal care vs preterm births

prenatal_care_ggplot = 
  plots_df %>% 
  ggplot(aes(x = late_no_prenatal_care, y = preterm_births, group = nta_name)) + 
  geom_point(color = "blue")

ggplotly(prenatal_care_ggplot)